Figure - available from: Neuroinformatics
This content is subject to copyright. Terms and conditions apply.
Source publication
Alzheimer’s disease (AD) is characterized by gradual neurodegeneration and loss of brain function, especially for memory during early stages. Regression analysis has been widely applied to AD research to relate clinical and biomarker data such as predicting cognitive outcomes from MRI measures. Recently, multi-task based feature learning (MTFL) met...
Similar publications
The task in referring expression comprehension is to localise the object instance in an image described by a referring expression phrased in natural language. As a language-to-vision matching task, the key to this problem is to learn a discriminative object feature that can adapt to the expression used. To avoid ambiguity, the expression normally t...
Citations
... Researchers have been interested in jointly applying AI-powered multi-task diagnostics and multimodal data fusion technologies to facilitate neurodegenerative disease prediction. For example, (Liu et al. 2019a) focused on multi-task feature learning by combining fused group lasso and ℓ2,1-norm with mixed norms to capture more adaptable structures. An alternating direction approach of multipliers was utilized to efficiently resolve non-smooth formulation. ...
Advancements in artificial intelligence (AI) have driven extensive research into developing diverse multimodal data analysis approaches for smart healthcare. There is a scarcity of large-scale analysis of literature in this field based on quantitative approaches. This study performed a bibliometric and topic modeling examination on 683 articles from 2002 to 2022, focusing on research topics and trends, journals, countries/regions, institutions, authors, and scientific collaborations. Results showed that, firstly, the number of articles has grown from 1 in 2002 to 220 in 2022, with a majority being published in interdisciplinary journals that link healthcare and medical research and information technology and AI. Secondly, the significant rise in the quantity of research articles can be attributed to the increasing contribution of scholars from non-English speaking countries/regions and the noteworthy contributions made by authors in the USA and India. Thirdly, researchers show a high interest in diverse research issues, especially, cross-modality magnetic resonance imaging (MRI) for brain tumor analysis, cancer prognosis through multi-dimensional data analysis, and AI-assisted diagnostics and personalization in healthcare, with each topic experiencing a significant increase in research interest. There is an emerging trend towards issues such as applying generative adversarial networks and contrastive learning for multimodal medical image fusion and synthesis and utilizing the combined spatiotemporal resolution of functional MRI and electroencephalogram in a data-centric manner. This study is valuable in enhancing researchers’ and practitioners’ understanding of the present focal points and upcoming trajectories in AI-powered smart healthcare based on multimodal data analysis.
... Stonnington [9] used CT as the import data of related vector regression (relevance vector regression, RVR) to predict the simple muscle tension checklist (MTAS), Alzheimer's Disease Rating Scale-cognitive scale (Alzheimer disease, assessment, scale-cognitive, ADAS-cog), and found that bilateral temporal lobe and hippocampus volume contributed significantly to the results. Liu [10] et al found that the top ten features with the greatest contribution were all located in the hippocampus. More accurate results and more abundant biomarkers are obtained than unimodal imaging data. ...
... Important aspects of brain networks have been chosen using sparse approaches, such as the least absolute shrinkage and selection operator (LASSO), because of the higher number of connectome features in the brain [9]. The LASSO regression analysis approach for feature selection and regularization can be used to choose nodal graph metrics and preserve strong discriminative nodal features [17]. In the recent past, methods to combine and identify brain regions have been developed using data-driven techniques and machine learning algorithms. ...
... The main objective of feature selection is to determine a few key features from the feature pool that will increase diagnostic accuracy. We used the group-LASSO [17] method for the nodal graph matrix and ensemble for genetic features that combines the feature subsets produced from various filters utilizing feature classes with those selected using various feature selection techniques (Chi-Square, InfoGain, and ReliefF) [34]. A brief explanation of each feature-selection method is provided below. ...
Mild cognitive impairment (MCI) precedes the Alzheimer’s disease (AD) continuum, making it crucial for therapeutic care to identify patients with MCI at risk of progression. We aim to create generalized models to identify patients with MCI who advance to AD using high-dimensional-data resting state functional magnetic resonance imaging (rs-fMRI) brain networks and gene expression. Studies that integrate genetic traits with brain imaging for clinical examination are limited, compared with most current research methodologies, employing separate or multi-imaging features for disease prognosis. Healthy controls (HCs) and the two phases of MCI (convertible and stable MCI) along with AD can be effectively diagnosed using genetic markers. The rs-fMRI-based brain functional connectome provides various information regarding brain networks and is utilized in combination with genetic factors to distinguish people with AD from HCs. The most discriminating network nodes are identified using the least absolute shrinkage and selection operator (LASSO). The most common brain areas for nodal detection in patients with AD are the middle temporal, inferior temporal, lingual, hippocampus, amygdala, and middle frontal gyri. The highest degree of discriminative power is demonstrated by the nodal graph metrics. Similarly, we propose an ensemble feature-ranking algorithm for high-dimensional genetic information. We use a multiple-kernel learning support vector machine to efficiently merge multipattern data. Using the suggested technique to distinguish AD from HCs produced combined features with a leave-one-out cross-validation (LOOCV) classification accuracy of 93.07% and area under the curve (AUC) of 95.13%, making it the most state-of-the-art technique in terms of diagnostic accuracy. Therefore, our proposed approach has high accuracy and is clinically relevant and efficient for identifying AD.
... Regression estimators with sparse constraints and robust properties play a central role in many high-dimensional signal processing applications, such as computational biology [1][2][3][4] and multitask learning [5][6][7][8]. In some statistical cases, only part of the observed variables are important to the prediction results, thus relevant variables can be grouped together, and all subsets of variables will be selected or discarded for regression. ...
... A supervised group lasso approach with a cluster structure was developed in [10] and applied in gene expression analysis for gene selection and predictive modeling. With the prior group structure of variables in the Alzheimer's Disease Neuroimaging Initiative (ADNI) clinical dataset, the multitask sparse group lasso [5,6] and the multitask fused group lasso [7] were employed to improve the cognitive performance prediction. Another multitask method was proposed in [8] to solve the overlapping group lasso problems and learn the relationship between tasks with an asymmetric structure estimation on the ADNI dataset. ...
... In this work, we employ the structure information described in [5][6][7][8]45] as the prior knowledge of the ADNI dataset. From the whole variable set, 46 groups have one covariate (subcortical volume, SV) and 70 groups have four covariates including the cortical thickness average (TA), Robust variable structure discovery based on tilted empirical risk minimization We focus on five widely used cognitive tasks based on the physical features of each individual's brain extracted from structural MRI images. ...
Robust group lasso regression plays an important role in high-dimensional regression modeling such as biological data analysis for disease diagnosis and gene expression. However, most existing methods are optimized with prior variable structure knowledge under the traditional empirical risk minimization (ERM) framework, in which the estimators are excessively dependent on prior structure information and sensitive to outliers. To address this issue, we propose a new robust variable structure discovery method for group lasso based on a convergent bilevel optimization framework. In this paper, we adopt tilted empirical risk minimization (TERM) as the target function to improve the robustness of the estimator by assigning less weight to the outliers. Moreover, we modify the TERM objective function to calculate its Fenchel conjugate while maintaining its robust property, which is proven theoretically and empirically. Experimental results on both synthetic and real-world datasets show that the proposed method can improve the robust performance on prediction and variable structure discovery compared to the existing techniques.
... ML algorithms used MRI for AD diagnosing. By the Neuroimaging data, an appliance of RNN algorithms was created to distinguish from healthy controls of AD patients [12] [13]. Further, the longitudinal EMRs were utilized to examine the course of persistent diseases including AD, and the Long Short-Term Memory (LSTM), Recurrent Neural Network (RNN) was found to be an excellent predictor of AD sequence by utilizing the medical and temporal patterns of patient visits. ...
... Prediction studies examining cognitive performance have reported similar R 2 values to our study comparing predicted with observed performance (Brickman et al. 2018;Duchesne et al. 2009;Stonnington et al. 2010). One recent study examined domain-specific cognitive performance using the Fused Group Lasso Regularized Multi-Task Feature Learning method, which explicitly modeled cognition as a multi-task feature learning problem (Liu et al. 2018). In contrast to these studies, the present study combined markers of gray matter atrophy and white matter injury, used data from a population-based study, compared biomarker-enhanced models with basic models, and conducted permutation tests to assess the prediction power of selected features. ...
High dimensional neuroimaging datasets and machine learning have been used to estimate and predict domain-specific cognition, but comparisons with simpler models composed of easy-to-measure variables are limited. Regularization methods in particular may help identify regions-of-interest related to domain-specific cognition. Using data from the Northern Manhattan Study, a cohort study of mostly Hispanic older adults, we compared three models estimating domain-specific cognitive performance: sociodemographics and APOE ε4 allele status (basic model), the basic model and MRI markers, and a model with only MRI markers. We used several machine learning methods to fit our regression models: elastic net, support vector regression, random forest, and principal components regression. Model performance was assessed with the RMSE, MAE, and R2 statistics using 5-fold cross-validation. To assess whether prediction models with imaging biomarkers were more predictive than prediction models built with randomly generated biomarkers, we refit the elastic net models using 1000 datasets with random biomarkers and compared the distribution of the RMSE and R2 in models using these random biomarkers to the RMSE and R2 from observed models. Basic models explained ~ 31–38% of the variance in domain-specific cognition. Addition of MRI markers did not improve estimation. However, elastic net models with only MRI markers performed significantly better than random MRI markers (one-sided P < .05) and yielded regions-of-interest consistent with previous literature and others not previously explored. Therefore, structural brain MRI markers may be more useful for etiological than predictive modeling.
... Decoding individuals' demographic (e.g., age, gender) and cognitive variables (e.g., IQ, attention ability) based on magnetic resonance imaging (MRI) has attracted much research interest in recent years (Dosenbach et al. 2010;Liu et al. 2016;Liu et al. 2019;Pereira et al. 2009;Tian et al. 2016;Yoo et al. 2018;Zhang et al. 2018). In studies on MRI-based decoding, it has often been a tricky problem to address the curse-of-dimensionality, as the number of features is usually much larger than the sample size (MouraO-Miranda et al. 2005;Pereira et al. 2009). ...
It has been a popular trend to decode individuals' demographic and cognitive variables based on MRI. Features extracted from MRI data are usually of high dimensionality, and dimensionality reduction (DR) is an effective way to deal with these high-dimensional features. Despite many supervised DR techniques for classification purposes, there is still a lack of supervised DR techniques for regression purposes. In this study, we advanced a novel supervised DR technique for regression purposes, namely, supervised multidimensional scaling (SMDS). The implementation of SMDS includes two steps: (1) evaluating pairwise distances among entities based on their labels and constructing a new space through a distance-preserving projection; (2) establishing an explicit linear relationship between the feature space and the new space. Based on this linear relationship, DR for test entities can be performed. We evaluated the performance of SMDS first on a synthetic dataset, and the results indicate that (1) SMDS is relatively robust to Gaussian noise existing in the features and labels; (2) the dimensionality of the new space exerts negligible influences upon SMDS; and (3) when the sample size is small, the performance of SMDS deteriorates with the increase of feature dimension. When applied to features extracted from resting state fMRI data for individual age predictions, SMDS was observed to outperform classic DR techniques, including principal component analysis, locally linear embedding and multidimensional scaling (MDS). Hopefully, SMDS can be widely used in studies on MRI-based predictions. Furthermore, novel supervised DR techniques for regression purposes can easily be developed by replacing MDS with other nonlinear DR techniques.
... , C. The group regularization technique allows us to estimate all parameters in a subset of parameters to be zero (see [52] for a review). A fused group regularization approach presupposes that either all differences γ ikc − γ ihc equal zero or all differences are estimated to be different from zero [53,54]. This property can be achieved by substituting a norm of the difference of the two vectors in the penalty. ...
The last series of Raven's standard progressive matrices (SPM-LS) test were studied with respect to its psychometric properties in a series of recent papers. In this paper, the SPM-LS dataset is analyzed with regularized latent class models (RLCM). For dichotomous item response data, an alternative estimation approach for RLCMs is proposed. For polytomous item responses, different alternatives for performing regularized latent class analysis are proposed. The usefulness of the proposed methods is demonstrated in a simulated data illustration and for the SPM-LS dataset. For the SPM-LS dataset, it turned out the regularized latent class model resulted in five partially ordered latent classes.
... Recent studies have started to use deep learning methods to predict individual differences in behavioral phenotypes and brain maturity. Based on neural networks, deep learning serves as an extension of traditional machine learning methods (98). Deep learning can automatically learn a higher level of abstract representation through the application of consecutive nonlinear transformations to raw input data in "hidden" neural network layers, making this approach ideally suited to detecting complex, scattered and subtle brain patterns (99). ...
The neuroimaging community has witnessed a paradigm shift in biomarker discovery from using traditional univariate brain mapping approaches to multivariate predictive models, allowing the field to move towards a translational neuroscience era. Regression-based multivariate models (hereafter "predictive modeling") provide a powerful and widely-used approach to predict human behavior with neuroimaging features. These studies maintain a focus on decoding individual differences in a continuously behavioral phenotype from neuroimaging data, opening up an exciting opportunity to describe the human brain at the single-subject level. In this survey, we provide an overview of recent studies that utilize machine learning approaches to identify neuroimaging predictors over the past decade. We first review regression-based approaches and highlight connectome-based predictive modeling (CPM), which has grown in popularity in recent years. Next, we systematically describe recent representative studies using these tools in the context of cognitive function, symptom severity, personality traits and emotion processing. Finally, we highlight a few challenges related to combining multimodal data, longitudinal prediction, external validations and the employment of deep learning methods that have emerged from our review of the existing literature, as well as present some promising and challenging future directions.
... Nodal graph metrics naturally have a group topology (i.e., a node corresponds to a group of node-graph theoretical attributes). Group-LASSO is a regression-analysis method for group-feature selection and regularization that can be adopted to select nodal graph metrics ( Liu et al., 2019) and maintain significant discrimination of nodal features. ...
Mild cognitive impairment (MCI) is often considered a critical time window for predicting early conversion to Alzheimer’s disease (AD). Brain functional connectome data (i.e., functional connections, global and nodal graph metrics) based on resting-state functional magnetic resonance imaging (rs-fMRI) provides numerous information about brain networks and has been used to discriminate normal controls (NCs) from subjects with MCI. In this paper, Student’s t-tests and group-least absolute shrinkage and selection operator (group-LASSO) were used to extract functional connections with significant differences and the most discriminative network nodes, respectively. Based on group-LASSO, the middle temporal, inferior temporal, lingual, posterior cingulate, and middle frontal gyri were the most predominant brain regions for nodal observation in MCI patients. Nodal graph metrics (within-module degree, participation coefficient, and degree centrality) showed the maximum discriminative ability. To effectively combine the multipattern information, we employed the multiple kernel learning support vector machine (MKL-SVM). Combined with functional connectome information, the MKL-SVM achieved a good classification performance (area under the receiving operating characteristic curve = 0.9728). Additionally, the altered brain connectome pattern revealed that functional connectivity was generally decreased in the whole-brain network, whereas graph theory topological attributes of some special nodes in the brain network were increased in MCI patients. Our findings demonstrate that optimal feature selection and combination of all connectome features (i.e., functional connections, global and nodal graph metrics) can achieve good performance in discriminating NCs from MCI subjects. Thus, the combination of functional connections and global and nodal graph metrics of brain networks can predict the occurrence of MCI and contribute to the early clinical diagnosis of AD.
